NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KZRZ8NSRJ8F2VCMSKCX2PJ
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2m 7s
Cost:
$0.020370
Provider:
Tencent
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The morning rush had faded at the small-town bakery, Flour & Fortune, leaving the scent of butter and cardamom lingering in the air. Sunlight pooled across the worn oak counter, and a single orange tabby slept atop a stack of recipe cards. Near the register, a crumb-covered note waited beside a cup of chamomile tea. The old safe behind the counter stood slightly ajar, its dial still warm. “Someone took the cinnamon roll recipe right out of the safe.” “Not just took it. They left that.” A nudge of a chin toward the glass case, where a smudge of lavender frosting marked the empty shelf. “Lavender? Nobody around here uses lavender except—” “Exactly. And the judge for the bake-off was found dozing in the town square with a pocketful of our stolen dough.” “That’s not proof. It’s pastry.” “It’s motive wrapped in buttercream. Someone wanted the blue ribbon badly enough to crumb the competition.” A pause. The tabby stretched, knocking a pencil onto the floor. “You think it was Mabel?” “I think we should check her apron pockets before the judging begins.” “Then let’s not crumb this investigation.” “Agreed. But first, another scone.” The tabby flicked an ear, as if it entirely agreed.
created_at
"2026-09-03T15:56:35.483Z"
9/3/2026, 3:56:35 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1713
moderation_latency
(null)
generation_time
126963
tokens_prompt
78
tokens_completion
7196
native_tokens_prompt
83
native_tokens_completion
8117
native_tokens_completion_images
(null)
native_tokens_reasoning
7825
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.020369839
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788450995-LawEnfJNSBLu0CAENtzQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788450995-LSV3eAzzlGHniHRmIrM7"
upstream_id
"e488b10b-9407-4ff9-89e8-a4b83fb0c89f"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"e488b10b-9407-4ff9-89e8-a4b83fb0c89f"
is_byok
false
latency
1713
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.020369839
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Tencent"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)